Lists the five DML privileges a MSSQL user holds on a database, schema-wide (SCHEMA::dbo) not per-table. Use it to audit user access before granting or revoking permissions.
List a MSSQL user's privileges on a database. Note: MSSQL's privilege model here is coarser than MySQL/Postgres - only these 5 DML permissions, applied schema-wide (SCHEMA::dbo), not per-table.
| Name | Required | Description | Default |
|---|---|---|---|
| db_name | Yes | ||
| db_username | Yes |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description has the full burden of disclosing tool behavior. It states the scope of what is listed (the 5 DML permissions applied via SCHEMA::dbo) and that the model is coarser than other systems. However, it does not explicitly state that listing is read-only, or how it behaves if the user or database does not exist.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two short, front-loaded sentences. The first sentence states the purpose, and the second provides the critical nuance about the coarse permission model. No wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has no output schema and no annotation, so the description should include enough to prepare the agent for the result. It mentions the 5 DML permissions and the schema-wide scope, but does not describe the exact return shape, possible errors, or failure conditions. It covers the essential context but leaves out detail that could be captured by a slightly richer description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema has 0% coverage for parameters, and the description does not compensate. It refers to 'a MSSQL user' and 'a database', but doesn't elaborate on db_username or db_name — e.g., whether the username should be a login or database user, whether the database must exist, or the format of the values. The description adds no real meaning beyond the parameter names.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states 'List a MSSQL user's privileges on a database' — a specific verb and resource. It also explicitly calls out that the model is coarser than MySQL/Postgres, which differentiates it from siblings such as ecp_mysql_list_privileges and ecp_postgres_list_privileges.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies that this tool is for MSSQL users and the note about coarse, schema-wide permissions hints at how it compares to MySQL/Postgres alternatives, but it never explicitly says 'use this for MSSQL' or 'for fine-grained per-table privileges, etc.' It does not name alternative tools. Use is more inferred than directly guided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.